Repository Index

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

• drug-discovery
• quantum-chemistry
• deep-learning
• biology

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

• pytorch
• protein-structure
• alphafold2

Scientific workflow engine designed for simplicity & scalability. Trivially transition between one off use cases to massive scale production environments

• workflow-execution
• workflow
• cloud
• hpc

[ICLR 2024] DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genome

• dataset
• dna
• dna-processing
• dna-training

Graph-linked unified embedding for single-cell multi-omics data integration

• bioinformatics
• deep-learning
• single-cell
• single-cell-multiomics

A Practical and Efficient NCBI Taxonomy Toolkit, also supports creating NCBI-style taxdump files for custom taxonomies like GTDB/ICTV

• bioinformatics
• taxonomy
• cross-platform
• lineage

Open Frontier Biomolecular Intelligence

scPerturb: A resource and a python/R tool for single-cell perturbation data

• cite-seq
• database
• perturbation
• scatac-seq

PhyloNetworks: a julia package with utilities for phylogenetic networks

LLM for Drug Editing, ICLR 2024

• chatgpt
• conversation
• drug
• drug-discovery

Data visualisation web components for the life sciences.

• biohackeu21
• bioinformatics
• visualization
• webcomponents

Accurate and efficient spot detection for microscopy data

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

• ai4science
• llm
• multiagent-systems
• prompt-engineering

NeuroAnatomy Toolbox: An R package for the (3D) visualisation and analysis of biological image data, especially tracings of single neurons.

• r
• neuroanatomy-toolbox
• cran
• neuron

The framework for quantification of neuronal anatomy

• neuroscience
• neuroanatomy-toolbox
• imagej
• imagej2

Official implementation of JAMIE, Joint variational Autoencoders for Multimodal Imputation and Embedding

• autoencoder
• imputation
• integration
• multimodal

DetecDiv provides a comprehensive set of tools to analyze time microscopy images using deep learning methods. The software structure is such that data can be processed either at the command line or using a graphical user-interface. Detecdiv classification models include : image classification and regression, semantic segmentation, LSTM networks to analyze data and image timeseries.

DeepAEG: A model for predicting cancer drug response based on data enhancement and edge-collaborative update strategies